2017/04/04 by Youness Mansar, Mansar, Youness, Lorenzo Gatti +7
Computer Science · #Sentiment Analysis and Opinion Mining #Advanced Text Analysis Techniques #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1704.00939
In this paper, we describe a methodology to infer Bullish or Bearish\nsentiment towards companies/brands. More specifically, our approach leverages\naffective lexica and word embeddings in combination with convolutional neural\nnetworks to infer the sentiment of financial news headlines towards a target\ncompany. Such architecture was used and evaluated in the context of the SemEval\n2017 challenge (task 5, subtask 2), in which it obtained the best performance.\n